Exploring Deep Neural Networks on Edge TPU

This paper explores the performance of Google's Edge TPU on feed forward neural networks. We consider Edge TPU as a hardware platform and explore different architectures of deep neural network classifiers, which traditionally has been a challenge to run on resource constrained edge devices. Based on the use of a joint-time-frequency data representation, also known as spectrogram, we explore the trade-off between classification performance and the energy consumed for inference. The energy efficiency of Edge TPU is compared with that of widely-used embedded CPU ARM Cortex-A53. Our results quantify the impact of neural network architectural specifications on the Edge TPU's performance, guiding decisions on the TPU's optimal operating point, where it can provide high classification accuracy with minimal energy consumption. Also, our evaluations highlight the crossover in performance between the Edge TPU and Cortex-A53, depending on the neural network specifications. Based on our analysis, we provide a decision chart to guide decisions on platform selection based on the model parameters and context.


page 3

page 4

page 5


Exploring Edge TPU for Network Intrusion Detection in IoT

This paper explores Google's Edge TPU for implementing a practical netwo...

Deep Learning-based Cattle Activity Classification Using Joint Time-frequency Data Representation

Automated cattle activity classification allows herders to continuously ...

Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model

Recently, there has been a trend of shifting the execution of deep learn...

Conditionally Deep Hybrid Neural Networks Across Edge and Cloud

The pervasiveness of "Internet-of-Things" in our daily life has led to a...

Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloud

Neural networks (NNs) are growing in importance and complexity. A neural...

Scientific Image Restoration Anywhere

The use of deep learning models within scientific experimental facilitie...

Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms

This paper introduces partitioning an inference task of a deep neural ne...

Please sign up or login with your details

Forgot password? Click here to reset